AI 연산을 DRAM 안에서 - GDDR6-AiM 기술 소개
Dive into SK하이닉스의 혁신적인 GDDR6-AiM 기술 개발과정과 PIM 구현방식을 통해 AI 연산의 효율성과 에너지 소비 개선방안을 탐구하는 기술 세션
Gravitonizer: Automated Cloud Cost Reduction Through AWS Graviton Migration
Discover how Gravitonizer automatically converts x86 applications to AWS Graviton, achieving up to 40% cloud cost reduction while maintaining performance. Learn about diagnosis, conversion, validation, and containerized deployment processes.
SK Hynix PIM (AiM) 기반 생성형 AI 모델 가속기 플랫폼
Discover SK하이닉스's innovative AiM-based accelerator platform, designed to overcome limitations in generative AI models like GPT through Processing-in-Memory technology, offering enhanced performance and energy efficiency.
Squash - 딥러닝 서비스 추론 속도 개선기
Discover how Squash technology optimizes deep learning inference speed and reduces hardware costs through innovative model compression techniques for efficient AI service deployment.
EdgeStack - 고성능 하이퍼 컨버지드 인프라 (HCI) 관리 솔루션
Discover EdgeStack, SKT's advanced HCI Cloud solution that virtualizes computing, network, and storage resources while supporting both X86 and ARM processors for efficient infrastructure management and workload optimization.
거대 인공지능 모델 시대에 스타트업의 차별화 방향 - AI 모델 경량화 기술을 중심으로
Discover how startups can differentiate through AI model optimization and edge computing, focusing on lightweight neural networks for wearable devices while maintaining high performance.
HMSDK: 2-Tier Memory System Optimization Solution for DRAM and CXL Memory
Discover HMSDK의 2-Tier 메모리 시스템 최적화 솔루션과 CXL 메모리 활용을 위한 API 및 라이브러리 구현 방법을 통해 데이터센터 성능 향상 방안을 탐구합니다.
Open-ISA RISC-V CPU 기반 DSA 개요 및 활용 예시 소개
Discover RISC-V CPU의 차별화된 활용 방안과 DSA 구현 전략을 통해 임베디드 시스템 설계의 새로운 가능성과 ARM 대비 장점을 파악하는 전문가의 통찰력 있는 분석.
Power Efficiency in vRAN and Open RAN Deployments - Arm and StarlingX Solutions
Discover how Arm and StarlingX collaborate to optimize power efficiency in vRAN and Open RAN deployments, exploring RISC-based solutions and energy-saving capabilities for telecom operators.
File System Acceleration Using Computational Storage for Efficient Data Storage
Explore file system acceleration techniques using computational storage, focusing on SmartSSD implementation for efficient compression and improved system performance through hardware offloading.
Breaking Through the Memory Wall with CXL - Accelerating Computing Performance
Discover how CXL-attached memory solutions overcome processor-memory bottlenecks, enabling enhanced performance for AI applications and in-memory databases in modern data centers.
Proprietary Interconnects and CXL: Evolution and Future Coexistence
Explore the evolution of open interconnects and CXL technology, examining their role alongside proprietary connectivity in modern compute architectures and future computing solutions.
CXL Accelerator-Based Memory Solutions - Bringing Unique Customer Value
Explore how VMware and Samsung leverage CXL Type-2 accelerator solutions to enhance memory capabilities, reduce costs, and improve workload performance through innovative hardware-software integration.
Revisiting XSAVE - Lessons from 20 Years of Processor Context State Management
Explore two decades of processor context state management, focusing on XSAVE's evolution and key insights for efficient system design and optimization.
A Status Update on the x86-cpuid-db Project
Explore the latest developments and progress of the x86-cpuid-db project, focusing on its impact and advancements in CPU identification.
Trusted I/O: Architectures and Implementations for Confidential Computing
Explore architectures and implementations for confidential computing, focusing on trusted I/O in secure environments.
Making Sense of Tristate Numbers (tnum)
Explore tristate numbers (tnum) and their applications in Linux systems with expert insights from YU, Shung-Hsi.
8-Bit Shack: New Software for the Apple II
Explore 8-Bit Shack's floppy disk production process for new and classic Apple II software, including custom packaging and on-demand services.
Static Analysis for CHERI - SOAP 2024
Explore custom static analyses supporting C/C++ code transition to CHERI hardware, enhancing memory protection and software compartmentalization for RISC-V and AArch64 architectures.
What We Learned from C++ Atomics and Memory Model Standardization
Explore insights from C++ atomics and memory model standardization, covering usage patterns, performance implications, implementation challenges, and lessons learned in language design.
Distributed and Parallel Image Processing on Livebook - ElixirConf EU 2023
Explore distributed and parallel image processing in Elixir using Livebook. Learn to implement face-hiding techniques with Nx and Evision, leveraging Flow for faster and more robust processing.